Doctors can detect heart failure from a single heartbeat with 100% accuracy using a new artificial intelligence-driven neural network.
That’s according to a recent study published in Biomedical Signal Processing and Control Journal, which explores how emerging technology can improve existing methods of detecting congestive heart failure.
Led by researchers at the Universities of Surrey, Warwick and Florence, it shows that AI can quickly and accurately identify CHF by analyzing one electrocardiogram (ECG) heartbeat.
CHF is a chronic progressive condition affecting the way in which blood is pumped around the body. Research shows that, in the US alone, around 5 million people live with it.
The researchers claim that clinical practitioners and health systems “urgently require efficient detection processes” as a result of “high prevalence, significant mortality rates and sustained healthcare costs”.
They believe that these concerns can be solved through the use of convolutional neural networks (CNN), which are more effective for identifying patterns and structures in data.
Unlike existing methods that are often time-consuming and inaccurate, their model combines advanced signal processing and machine learning tools on raw ECG signals to improve detection rates dramatically.
Dr Sebastiano Massaro, associate professor of organizational neuroscience at the University of Surrey, said: “First, by assessing ECG directly, we confirm that with AI it is possible to accurately detect CHF looking beyond heart rate variability analysis. Thus, we have in general results that are more adherent to the real behavior of the affected heart.”
In another part of the experiment, a specific CNN model was used to improve the accuracy of CHF detection while taking into account comparable models.
“We focus on the detection of the pathology from one single heartbeat in excerpts of 5-minutes rather than in 24-hours recordings,” said Massaro.
“This aspect offers a valuable potential for prospects of rapid interventions; nonetheless it is also important to keep in mind that we are talking about severe CHF patients only at the moment.”
Going forward, Massaro hopes to extend the approach to largescale samples and other classes of CHF so that the technology can eventually be implemented in everyday healthcare systems and practices.
He added: “The application of organizational neuroscience, and specifically of neural network approaches to healthcare issues promises to open breakthrough frontiers for both clinical research and practice.”